Pixart-xl-2-1024-ms-q4_k_m-4Bit

Accuracy vs. Size Tradeoff

Every variant is benchmarked against the FP16 baseline. Choose the right balance of accuracy and footprint for your workflow.

Usage Code Snippets

Which variant for your hardware?

Choose the right quantization path for your device and performance target.

About This Model

PixArt-XL-2-1024-MS is an open-weight text-to-image foundation model developed by the PixArt research team. Built on a Diffusion Transformer (DiT) architecture, the model is designed to generate high-quality 1024×1024 images while maintaining significantly lower computational requirements than larger image generation models. The model utilizes T5 text encoders and a transformer-based diffusion backbone to achieve strong prompt understanding, photorealistic rendering, artistic image generation, concept visualization, and creative content production. The GGUF quantized version enables lightweight deployment through ComfyUI-GGUF and local inference environments, making it an attractive choice for users with limited GPU memory. PixArt-XL became one of the earliest successful open-source DiT-based image generation models and remains popular for efficient local image synthesis workflows.